Joint Estimation of State and Sensor Systematic Error in Hybrid System

Size: px
Start display at page:

Download "Joint Estimation of State and Sensor Systematic Error in Hybrid System"

Transcription

1 Joint Estiation of State and Sensor Systeatic Error in Hybrid Syste Lin Zhou, Quan Pan, Yan Liang, Zhen-lu Jin School of utoation Northwestern Polytechnical University Xi an, 77, China bstract Consider the hybrid systes with nonlinear property, and the sensor easureents with unnown and tie-varying systeatic error in this paper. In order to obtain the joint least square (LS) estiation of state and systeatic error, a new ethod JE-EM (joint estiation-expectation axiization) is proposed. In this paper, the relationship between the sensor systeatic error estiation and state estiation is derived, which can be described by the fraewor of EM. Due to the character of the hybrid syste, the target state is estiated by the IMM with PF filter. ased on the above relationship, systeatic error is iteratively estiated by the fraewor of EM. Siulation results with a aneuvering target tracing scenario show the effectiveness of the proposed ethod. Keywords- Hybrid syste;systeatic error;interacting ultiple odel (IMM);Particle filter (PF);Expectation axiization (EM) I. INTRODUCTION In the integrated air surveillance syste, data fusion is an iportant issue in the sensor networ research field. The sensor easureents are collected by distributed sensors. However, sensor easureents include rando and systeatic error, and if aforeentioned easureents are not odified, these errors lead to degradation in trac inaccuracy perforance and even ay bring out ghost targets. In order to iprove the fusion precise of ultiple sensors, it is vital to eliinate errors. Rando errors can be solved by soe filtering algoriths, and sensor alignent ethods are used to deal with systeatic error. Sensor alignent is referred to as the registration proble, and it is an inherent proble in ulti-sensor syste, besides, it deals with the correction of registration errors. The sensor easureents after registered are vital that they are concerned with data correlation, trac anageent, target detection and filtering, classify and tracing, and so on. Many successful sensor registration algoriths have been proposed in literatures. The standard registration approach is the real tie quality control (RTQC) []. In [], Leung developed the least square (LS) ethod. The generalized least square (GLS) is given by ar-shalo [3], and Zhou advanced an algorith which was GLS based on earth-centered earth-fixed (ECEF-GLS) [4, 5]. esides, in [6], the exact axiu lielihood (EML) ethod incorporated the effects of easureent noise was proposed in 3. The aforeentioned algoriths are offline registration ethods. t the sae tie, there are soe online registration ethods. The Kalan filter (KF) [6] was usually used to estiate systeatic error. The extended Kalan filter (EKF) [8, 9] and the particle filter (PF) [5], which usually used to estiate the states of the augented in nonlinear syste. The siulated annealing and particle swar optiization (S-PSO) was proposed in [], it solved the proble of variant systeatic error registration, and overcae the defect of local optiu estiation, besides, avoided population degradation on particles. In [], Ignagni assued target state and systeatic error are initially uncorrelated, and developed the decoupled Kalan filter (DKF), which perfored two estiation schees including target state and systeatic error. In [, 3], the exact ethod (EX) and iproved EX were provided, the systeatic error estiation were accoplished by the local state estiation such that they yielded pseudoeasureents of the systeatic error with additive noises. In [4], He expressed the effect caused by radar systeatic error as rotation and ass otion between target tracs fro radars, and he proposed the Fourier transforation approach to estiate and copensate the rotation and ass otion between the target tracs and fusion center. esides, a series of ethods have been provided to jointly estiate target state and systeatic error. In [6], the augented state Kalan filter (SKF) ethod stac target state and sensors systeatic error into a single vector. In [7], Li had given the augented state unscented Kalan filter (SUKF), which was used to estiate the state of the augented nonlinear syste. In ultisensory surveillance, the exact axiu Kalan filter (EM-KF) [8] approach was provided to jointly solve data association, registration, and data fusion. In [9], Oello gave the axiu lielihood registration (MLR) with the arbitrary target state otion, the arbitrary nuber and types of sensors. These ethods have been used to solve sensor registration. However they are applied in the very restricted conditions. For instance, tie invariant systeatic error, siplified otion odel of target, nown statistic distribution of systeatic noise, and so on. In practice, any factors which affect sensors systeatic error are uncertainty. For exaple, the cliate, the terrain, the ray of different region, the property of nonlinear and ultiple odels, and so on. So, aforeentioned ethods are no longer adequate to solve sensor registration, and even worse can cause the fresh easureent errors. In the real applications, the transforation between otion odels has the property of stochastic or eergence which This paper is supported by National Natural Science Foundation of China (No. 635 No No. 6759). 969

2 leads to the syste with the character of nonlinear and ultiple odels. The aforeentioned syste is called hybrid syste, i.e. the traditional algoriths are not adequate to estiate systeatic error in hybrid syste. Otherwise, systeatic error estiation will produce serious deviation and decrease the precision of target tracing. The hybrid syste has been recently applied in ilitary civil fields with coplex environent. In order to iprove the precision of capturing and odify easureents, any aneuvering target tracing techniques have been developed. Either the target state or the systeatic error can be estiated in these ethods. Nevertheless, ost of traditional ethods cannot deal with the interaction of target state and systeatic error, for exaple, SKF or SUKF, and so on. To solve the proble, Song and Li [6,7] give the joint estiation ethods of state and systeatic error by EKF and UKF algoriths, however, syste noise is liited to a certain case. Li [8] proposed an algorith with the joint of data association, registration, and fusion using EM-KF, however, the ultiple odels of syste was not taen into account. Consider the hybrid syste with nonlinear property and ultiple odels, a new joint estiation-expectation axiization ethod is proposed. The target state and sensor systeatic error are jointly estiated here. In order to iprove the estiation results and solve the proble of nonlinear and the ultiple odels, both the EM, and IMM with PF are applied in this wor.this paper is organized as follows. In section II, we derive the relationship between state estiation and systeatic error estiation. We describe the steps of algorith in section III. Section IV illustrates the perforance of feasibility and efficiency based on the siulation scene. II. PRMETER ESTIMTION. Proble Stateent It is assued that target state contains ultiple odels, and sensor easureents involve systeatic error and nonlinear. In a hybrid stochastic syste with additive noise can be expressed by x = F x + Γ u =,,, M. (),,, where x represents target state at tie, and a noisy sensor easureent with additive systeatic error has the for z = h ( x) + b + v. () where represents the target otion odel and it is a hoogeneous Marov chain with transition probability as follows P{ }= π. (3) where,,,, M, and M is the set of odal states. F, is the nown state transition atrix, Γ, is the input control atrix related to odel. u, is the process noise with zero-ean and Gaussian covariance. The nonlinear vector function atrix h is a nown Q, s ri atrix ( r i represents state diension with odel). The sensor systeatic error b is a s vector, and it is independent of u,. The noise v is a Gaussian rando vector with zeroean and covariance R, and it is independent of u.,. Relationship of State Estiation and Systeatic Error Estiation In assued hybrid syste, target state and systeatic error are unnown paraeters. Due to the unnown systeatic error estiation, it is ipossible to estiate state by classic filter ethod i.e. KF, SKF, and so on. In order to jointly estiate state and systeatic error, it is necessary to give the relationship of state estiate and systeatic error estiation. We rewrite () as follows b = z h x + v = z h xˆ + h x h xˆ + v. (4) The systeatic error estiation can be calculated by the conditional expectation of systeatic error ˆ K b = E b Z K = z h xˆ + E h x Z h x ˆ. (5) ( ) if the condition blow is satisfied Eh ( K x Z ) = E h ( x ˆ). (6) then equation (5) can be rewrote as = z h xˆ. (7) is the least square (LS) estiation at the oent. C. EM pproach to Recursive Estiation The state estiation xˆ can be estiated by the filter. f xˆ, z, b ˆ as filter, and substitute it into (7), we Denote ( ) have ( ( ˆ ˆ,, )) = z h f x z b. (8) where xˆ is state estiation at tie. The equation (8) is nonlinear, so we copute systeatic error estiation by iterative ethod as follows, and ipleent until it converges to perfect results ˆ ( p+ ) ˆ,, ˆ ( p b = z h f x z b ). (9) ( ( )) where p corresponds to the p -th iteration. Due to the state estiation xˆ can be estiated by the filter ( ˆ ˆ,, ) the relationship between iteration has the for xˆ and ( ˆ ˆ,, ) f x z b, f x z b at the p -th ( ˆ p ) xˆ = f xˆ, z, b. () ( p ) Due to the expectation axiization (EM) [] algorith is an iterative procedure that estiates both the paraeters 97

3 and the issing or unobservable data during an iteration. Now, the joint estiation can be described by the two iterative steps E-Step: M-Step: ( ˆ p { )} xˆ = E f xˆ, z, b. () ( p ) ( ˆ p { ( ˆ ))} = arg ax z h f x, z, b. () ( p+ ) ˆ( p ) In the start of iteration, we replace b with initialization estiation b initial, and calculate state estiation x ˆ in the E- f xˆ, z, b ˆ, and update systeatic error Step by the filter ( ) estiation in the M-Step. D. State Estiation by IMM-PF Due to the hybrid syste with ultiple otion odels, in order to estiate state, the IMM tracer is the best solution to solve proble. It is necessary to interactively process the state estiation according to the odel transition probability π fro - to. Then, we copute the odel ixing probability π and the state ixing estiation x, with odel at tie. It is assued that the syste has nonlinear property and contains non-gauss syste noise, and then this paper adopts the particle filter (PF). The PF avoids soe probles including linearization error, syste noise restriction, and so no. In fact, the PF is the ethod of the optiization recursion ayesian filter based on Monte Carlo siulation. fter generating x,, we consider x, as the input () () of PF, and obtain particles x,,,,, x x,. It is necessary to update the above particles and obtain the () () ( N ) prediction x,,,,, x x, at tie. Note that N is the particle nuber with odel. ( N ) For odel, we have the output of PF x ˆ as N ( n) =, n= x xˆ x N. (3) fter getting ˆ, we utilize the odel probability odel and copute the fusion state estiation u with M = u ˆ = xˆ x. (4) where u is the updated odel probability, and it is coputed by the equation as follows u = Λ c. (5) c M where c = π u and c = Λ = M = lielihood probability Λ is as follows c T -. The odel Λ = exp{ v S v }. (6) s ( π) S S N ( n) (, ) ˆ = N n= N ( () ) ( () T n ˆ n,, ) ˆ = N n= In (6), the easureent residual v and the estiation covariance can be coputed by the denoted expression v z h x b. (7) S z h x b z h x b. (8) Note that is the unnown systeatic error estiation in (7) and (8), therefore, v and S cannot be directly coputed. However, we can replace with arbitrary initialization b initial. Substituting the arbitrary initialization of systeatic error in E-Step, we get the state estiation xˆ by the IMM-PF ethod. III. JOINT ESTIMTION LGORITHM OF STTE ND SYSTEMTIC ERROR In order to jointly estiate the state and the systeatic error, the target state estiation can be coputed by using particle filter (PF) based on interacting ultiple odel (IMM) at first. Then, the relationship between the sensor systeatic error estiation and state estiation is derived by above EM steps, and it is used for the optiizing process of joint estiation. The steps of the proposed algorith as follows: Paraeters initialization; FOR =,3,, K Model conditional re-initialization <> Copute the odel ixing probabilityπ using u and π ; <> Copute the state ixing estiation x, using () the interaction input state x ˆ, the state () P, covariance, and π,; Setting repetition label flag ; WHILE e Maxn, and flag is true Setting repetition label flagcore ; WHILE e < 3 or flagcore is true Model conditional filtering <> State saple:, 97

4 Randoly saple fro x, to get the state particles,,,,,,, N,, x x x ; <> The state particle update: Transit particles x,,, x,,,, x N,, to ( e) ( e) ( e),,,,,,, N,, x x x ; Re-saple ( e) ( e) ( e),,,,,,, N,, x x x to obtain ( e ) ( e ) ( e ),,,,,,, N,, x x x ; Copute the state estiation x ˆ, the easureent residual covariance v S using (3), (7), (8);, and the estiation Copute the lielihood function of easureent by (6) Model probability update: Update the state odel probability u by (5); Estiation fusion Copute the fusion state estiation x using x ˆ, P, and u, and (4); ˆ( e ) ˆ e Calculating systeatic error b by (); Condition judgent: Let e = e+ ; if e 3 then reset flagcore ; END WHILE Condition judgent: Let e = e ; If ˆ ( e ) ˆ ( e b = b ) or e = Maxn then we calculate the fusion systeatic error estiation and consider it as the initialization b + at tie +, besides, reset flag ; Update repetition paraeters : Reset flagcore, and Let e = e+ ; END WHILE END FOR where e expresses the EM iterative tie, and Maxn is the axiu iterative tie. IV. SIMULTION RESULTS. Proble Stateent In this section, it is assued that the otion of the aneuver target is restricted to the horizontal plane. We desire to trac target based on the polar easureents fro the radar, and the easureents contain systeatic error. In hybrid syste with additive stochastic noise, the target state evolves according to the odel as follows Fx + Γu, 3 x = Fx + Γu, 3 < 4 Fx + Γu, 4 < Two different state transition atrixes are given as follows, and τ = is the sapling tie interval τ F = τ sin( ωτ ) ω (cos( ωτ ) ) ω cos( ωτ ) sin( ωτ ) F = ( cos( ωτ )) ω sin( ωτ ) ω sin( ωτ ) cos( ωτ ) There, Γ is input control atrix τ τ Γ = τ τ Let x [ ] T = x x y y be the state vector of target, and x, y, x, y represents the orthogonal coordinates and coordinates direction velocity of the horizontal plane, respectively. Note that between scans and 3, the target is constant velocity otion, and velocity coponent is x =.3 / s, y =. / s, respectively. Fro scan 3 to scan 4, the target is aneuvering curve otion, and angular velocity ω is.5rad/s. fter scan 4, the target is such otion as the first period. The process noise u, and u, are belonging to the above different odels, the covariances are given below Q = diag([.6,.6 ]), Q = Q In polar coordinate, the easureent odel with additive systeatic error has the for z h ( x ) Z = = + b + v z h ( x ) = = ( x x) + ( y y) r = = y y θ tan x x x y y is state vector with initialization ( x x) + ( y y) r ( ) y y θ tan x x h x h x where [ ] T x = x T x = [35.3 / s], T x = [. / s] ;( x, y) and ( x, y ) are the location of two radars 97

5 with x = 5, y =, x = 3, y = 65 ; T = [ Δ, Δ ] r θ b b b is systeatic error vector and Δ b = [ Δ ; Δ ], Δ b = [ Δr ; Δθ ]; v is a white, zeroean Gaussian sequence with nown covariance R = diag([ R ]), R = R θ = diag([(. ) (. ) ]) ; Z r R θ T = [ r, θ, r, θ ] r is the sensor easureent vector in polar plane, r, θ, r, θ are the ranges and aziuths of sensor and, respectively. The transition probability of Marov chain is π ij = [.99.;..99] in IMM, and the probability atrix of two odels is u = [.5.5]. The initialization target T state estiation is xˆ = x ˆ = [ x,, y,], where z z xz and Z are the orthogonal coordinates of easureent at first saple tie, and initialization covariance atrix is P = diag([ Pinit P init ]), P init = [.. / s ].The sapler particle nuber N is 3. The siulation step is 3 6. The EM iterative tie is. esides, the Monte Carlo tie is 5.. Siulation Results ccording to given paraeters, target real trajectory of single step is shown in Figure. y() Trac-Real Sensor Sensor x() Figure. Target real trajectory It is assued that the systeatic error is tie-varying, and it has expression b = + F b + b v b where Fb is systeatic error transition atrix, and it is T diag([ I I ]) ; systeatic error vector b = [ b, b ], it has initialization value [,,.5,.8 ] T ; systeatic error b noise v is a white, zero-ean Gaussian sequence with nown covariance R b = diag([(.5 ) (.8 ) (.8 ) (.6 ) ]). We get the corresponding results of tie-varying systeatic error based on assued paraeters shown in Figure. y z Range-error() Range-error().5.5 Sensor ziuth-error( ) ziuth-error( ).5.5 Sensor Figure. Systeatic error on range and aziuth fter jointly estiate state and systeatic error based on JE-EM proposed in this paper, it ipleents the systeatic error registration of sensor and. fter single step, the Figure 3 gives the coparison trajectory aong real, unregistered, and registered easureent. It shows that the registered easureent is better than the unregistered. y() Real Measureent- Measureent- Registrated easureent- Registrated easureent- Sensor Sensor x() Figure 3. The coparison trajectory of real, unregistered easureent, and registered easureent We obtain the systeatic error estiation using the proposed ethod. Figure 4 gives the coparison of estiation and assued systeatic error. Range-error() Range-error() Real() Estiation - 3 Real() Estiation ziuth-error( ) ziuth-error( ) 3 Real() Estiation - Real() Estiation - Figure 4. The systeatic error coparison of real and estiation 973

6 Range-error() Range-error() Sensor ziuth-error( ) ziuth-error( ) - Sensor Figure 5. Systeatic error deviation of real and estiation ccording to Figure 4, the Figure 5 is the systeatic error deviation of systeatic error estiation and assued systeatic error. In Figure 5, the range deviation scope is ~., the aziuth deviation approxiately is., and sensor and have average range deviations.45,.6, and aziuth deviation.,., respectively. Copare the range deviation and aziuth deviation with the assued systeatic errors resolution (sensor has resolution.5 and.8, sensor has resolution.8 and.6 ), the above deviations are uch lesser. Siulation results reveal that the JE-EM algorith can preferably estiate systeatic error of sensor and sensor. In conclusion, utilizing the iterative property of EM and the relationship between state estiation and systeatic error estiation, we can iteratively update state estiation and systeatic error estiation at every sapling tie. fter 5 ties Monte Carlo, Figure 6 gives the RMSE of distance, velocity on X and Y axes, respectively. In Figure 6, the RMSE of target state estiation have sharp decline excluding the velocity of Y axes on sensor at the start. The average runtie is 56.73s after 5 ties siulation, and the average RMSE of target state estiation on X and Y axes as TLE I. RMSE-X() RMSE-Y() Sensor Sensor- 5 5 RMSE-Vx(/s) RMSE-Vy(/s) Sensor Sensor- 5 5 (a) Sensor RMSE-X() RMSE-Y() TLE I. RMSE RMSE-Vx(/s) RMSE-Vy(/s) (b) Sensor Figure 6. RMSE of target state estiation X axes () RMSE VERGE OF TRGET STTE ESTIMTION X axes velocity (/s) Y axes () Y axes velocity (/s) Sensor Sensor The RMSE of tie-varying systeatic error after 5 ties Monte Carlo as Figure 7. In Figure 7, we can see the RMSE of systeatic errors have a sharp decline at the start. Subsequently, curve preservers around the certain value. RMSE-Range() RMSE-ziuth( ) RMSE-Range() RMSE-ziuth( ).5 Sensor Sensor (a) Sensor (b) Sensor Figure 7. RMSE of systeatic error 974

7 ccording the RMSE of sensor systeatic error estiation after 5 ties Monte Carlo, we get the average RMSE of range errors and aziuth errors as follows in TLE II. TLE II. RMSE VERGE OF SYSTEMTIC ERROR ESTIMTION RMSE Range error() ziuth error( ) Sensor.79.8 Sensor.8.3 V. CONCLUSION In the real applications, a lot of stochastic or eergent factors cause the otion odels transferring in any hybrid systes, which produces serious estiation deviation and decreases tracing precision. new ethod called JE-EM is introduced to solve this proble. In this wor, the ultiple odels and the nonlinear property are taen into account in dynaic hybrid syste. We estiate state by IMM with PF ethod in this paper. Then, the relationship between the target state estiation and systeatic error estiation are derived, and this relationship can be described by the fraewor of EM, and it can be used to optiize the joint estiation. The proposed ethod is used to update the unregistered easureents with systeatic error. The updated easureents can provide ore reliable inforation to soe wors, i.e. easureent associating, target tracing, and so on. [] X.D. Lin, Y. ar-shalo, T.Kirubarajan, Exact ultisensor dynaic bias estiation with local tracs, IEEE Transactions on erospace and Electronic Systes, vol.39, no.4, 4, pp [3] X.D. Lin, Y. ar-shalo, T.Kirubarajan, Multisensor-ultitarget bias estiaiton for general asynchronous sensors, IEEE Transactions on erospace and Electronic Systes, vol.4, no.3, 6, pp [4] Y. He, Q. Song, W. Xiong, trac registration-correlation algorith based on Fourier transfor, cta eronautica Et stronautica Sinica, vol.3, no.,, pp [5]. Zia, T. Kirubarajan, P. Reilly, Jaes, D. Yee, et al, n EM algorith for nonlinear state estiation with odel uncertainties, IEEE Transactions on Signal Processing, vol.56, no.3, 8, pp [6] Q. Song, Y. He, Y.L. Dong, n joint estiation algorith for state and systeatic errors, Journal of Projectiles, Rocets, Missiles and Guidance, vol.7, no.4, 7, pp [7] W. Li, H. Leung, Y. Zhou, Space-tie registration of radar and ESM using unscented Kalan filter, IEEE Transactions erospace and Electronic Systes, vol. 4, no.3, 4, pp ,. [8] Z. H. Li, S. Y. Chen, H. Leung, Joint data association, registration, and fusion using EM-KF, IEEE Transactions on erospace and Electronic Systes, vol.46, no.,, pp [9] N. Oello,.Ristic, Maxiu lielihood registration for ultiple dissiilar sensors, IEEE Transactions on aerospace and electronic systes, vol.39, no.3, 3, pp [] P. Depster, N. Laird, D.Rubin, Maxiu lielihood fro incoplete data via the EM algorith, J. Roy. Stat., vol.39, 977, pp REFERENCES [] J J. ure, The SGE real tie quality control function and its interface with UIC II/UIC-III, MITRE Corporation Technical Report, No.38, London, England, Noveber 996. [] H. Leung, M. lanchett, least square fusion of ultiple radar data, Proceeding of Radar 94, Paris, 994, pp [3] Y.ar-Shalo, Multitarget-ultisensor tracing: advanced applications, in Registration:a prerequisite for ultiple sensor tracing, M. P.Dana, Norwood, M: rtech House, 99. [4] Y.F. Zhou, L. Henry,.Martin, Sensor alignent with earth-centered earth-fixed (ECEF) coordinate syste, IEEE Transactions on erospace and Electronic Systes, vol. 35, no., 993,pp [5] I.T.Li, J. Georganas, Multi-target Multi-platfor sensor registration in geodetic coordinates, Proceedings of the Fifth International Conference on Inforation Fusion, vol., no.,, pp [6] N. Oello,. Ristic, Maxiu lielihood registration for ultiple dissiilar sensors, IEEE Transactions on erospace and Electronic Systes, vol.39, no.3, 3, pp [7] S. Dhar, pplication of a recursive ethod for registration error correction in tracing with ultiple sensors, Proceeding of erican Control Conference, San Francisco, C, 993, pp [8] E. J. Dela Cruz,. T. louani, T. R. Rice, W. D. lair, Sensor registration in ultisensor systes, Proceeding of SPIE Conference on Signal and Data Processing of Sall Targets, Orlando, FL, US, 99, pp [9].Friedland, Treatent of bias in recursive filtering, IEEE Transactions on utoatic Control, vol.4, no.4, 969, pp [] L. Zhou, Q. Pan, Y. Liang, pplication of iproved S-PSO in the syste error registration, Opto-Electronic Engineering, vol.37, no.9,, pp [] M.. Ignagni, n alternate derivation and extension of Friedland s two-stage alan estiator, IEEE Transactions on utoatic Control, vol.6, no.3, 98, pp

Identical Maximum Likelihood State Estimation Based on Incremental Finite Mixture Model in PHD Filter

Identical Maximum Likelihood State Estimation Based on Incremental Finite Mixture Model in PHD Filter Identical Maxiu Lielihood State Estiation Based on Increental Finite Mixture Model in PHD Filter Gang Wu Eail: xjtuwugang@gail.co Jing Liu Eail: elelj20080730@ail.xjtu.edu.cn Chongzhao Han Eail: czhan@ail.xjtu.edu.cn

More information

An Improved Particle Filter with Applications in Ballistic Target Tracking

An Improved Particle Filter with Applications in Ballistic Target Tracking Sensors & ransducers Vol. 72 Issue 6 June 204 pp. 96-20 Sensors & ransducers 204 by IFSA Publishing S. L. http://www.sensorsportal.co An Iproved Particle Filter with Applications in Ballistic arget racing

More information

Department of Electronic and Optical Engineering, Ordnance Engineering College, Shijiazhuang, , China

Department of Electronic and Optical Engineering, Ordnance Engineering College, Shijiazhuang, , China 6th International Conference on Machinery, Materials, Environent, Biotechnology and Coputer (MMEBC 06) Solving Multi-Sensor Multi-Target Assignent Proble Based on Copositive Cobat Efficiency and QPSO Algorith

More information

Tracking using CONDENSATION: Conditional Density Propagation

Tracking using CONDENSATION: Conditional Density Propagation Tracking using CONDENSATION: Conditional Density Propagation Goal Model-based visual tracking in dense clutter at near video frae rates M. Isard and A. Blake, CONDENSATION Conditional density propagation

More information

An Adaptive UKF Algorithm for the State and Parameter Estimations of a Mobile Robot

An Adaptive UKF Algorithm for the State and Parameter Estimations of a Mobile Robot Vol. 34, No. 1 ACTA AUTOMATICA SINICA January, 2008 An Adaptive UKF Algorith for the State and Paraeter Estiations of a Mobile Robot SONG Qi 1, 2 HAN Jian-Da 1 Abstract For iproving the estiation accuracy

More information

Effective joint probabilistic data association using maximum a posteriori estimates of target states

Effective joint probabilistic data association using maximum a posteriori estimates of target states Effective joint probabilistic data association using axiu a posteriori estiates of target states 1 Viji Paul Panakkal, 2 Rajbabu Velurugan 1 Central Research Laboratory, Bharat Electronics Ltd., Bangalore,

More information

International Journal of Scientific & Engineering Research, Volume 4, Issue 9, September ISSN

International Journal of Scientific & Engineering Research, Volume 4, Issue 9, September ISSN International Journal of Scientific & Engineering Research, Volue 4, Issue 9, Septeber-3 44 ISSN 9-558 he unscented Kalan Filter for the Estiation the States of he Boiler-urbin Model Halieh Noorohaadi,

More information

Block designs and statistics

Block designs and statistics Bloc designs and statistics Notes for Math 447 May 3, 2011 The ain paraeters of a bloc design are nuber of varieties v, bloc size, nuber of blocs b. A design is built on a set of v eleents. Each eleent

More information

Filtering and Fusion based Reconstruction of Angle of Attack

Filtering and Fusion based Reconstruction of Angle of Attack Filtering and Fusion based Reconstruction of Angle of Attack N Shantha Kuar Scientist, FMC Division NAL, Bangalore 7 E-ail: nskuar@css.nal.res.in Girija G Scientist, FMC Division NAL, Bangalore 7 E-ail:

More information

e-companion ONLY AVAILABLE IN ELECTRONIC FORM

e-companion ONLY AVAILABLE IN ELECTRONIC FORM OPERATIONS RESEARCH doi 10.1287/opre.1070.0427ec pp. ec1 ec5 e-copanion ONLY AVAILABLE IN ELECTRONIC FORM infors 07 INFORMS Electronic Copanion A Learning Approach for Interactive Marketing to a Custoer

More information

Experimental Design For Model Discrimination And Precise Parameter Estimation In WDS Analysis

Experimental Design For Model Discrimination And Precise Parameter Estimation In WDS Analysis City University of New York (CUNY) CUNY Acadeic Works International Conference on Hydroinforatics 8-1-2014 Experiental Design For Model Discriination And Precise Paraeter Estiation In WDS Analysis Giovanna

More information

Feature Extraction Techniques

Feature Extraction Techniques Feature Extraction Techniques Unsupervised Learning II Feature Extraction Unsupervised ethods can also be used to find features which can be useful for categorization. There are unsupervised ethods that

More information

SEISMIC FRAGILITY ANALYSIS

SEISMIC FRAGILITY ANALYSIS 9 th ASCE Specialty Conference on Probabilistic Mechanics and Structural Reliability PMC24 SEISMIC FRAGILITY ANALYSIS C. Kafali, Student M. ASCE Cornell University, Ithaca, NY 483 ck22@cornell.edu M. Grigoriu,

More information

Uncertainty Propagation and Nonlinear Filtering for Space Navigation using Differential Algebra

Uncertainty Propagation and Nonlinear Filtering for Space Navigation using Differential Algebra Uncertainty Propagation and Nonlinear Filtering for Space Navigation using Differential Algebra M. Valli, R. Arellin, P. Di Lizia and M. R. Lavagna Departent of Aerospace Engineering, Politecnico di Milano

More information

An improved self-adaptive harmony search algorithm for joint replenishment problems

An improved self-adaptive harmony search algorithm for joint replenishment problems An iproved self-adaptive harony search algorith for joint replenishent probles Lin Wang School of Manageent, Huazhong University of Science & Technology zhoulearner@gail.co Xiaojian Zhou School of Manageent,

More information

CS Lecture 13. More Maximum Likelihood

CS Lecture 13. More Maximum Likelihood CS 6347 Lecture 13 More Maxiu Likelihood Recap Last tie: Introduction to axiu likelihood estiation MLE for Bayesian networks Optial CPTs correspond to epirical counts Today: MLE for CRFs 2 Maxiu Likelihood

More information

(6) B NN (x, k) = Tp 2 M 1

(6) B NN (x, k) = Tp 2 M 1 MMAR 26 12th IEEE International Conference on Methods and Models in Autoation and Robotics 28-31 August 26 Międzyzdroje, Poland Synthesis of Sliding Mode Control of Robot with Neural Networ Model Jaub

More information

Ufuk Demirci* and Feza Kerestecioglu**

Ufuk Demirci* and Feza Kerestecioglu** 1 INDIRECT ADAPTIVE CONTROL OF MISSILES Ufuk Deirci* and Feza Kerestecioglu** *Turkish Navy Guided Missile Test Station, Beykoz, Istanbul, TURKEY **Departent of Electrical and Electronics Engineering,

More information

Intelligent Systems: Reasoning and Recognition. Perceptrons and Support Vector Machines

Intelligent Systems: Reasoning and Recognition. Perceptrons and Support Vector Machines Intelligent Systes: Reasoning and Recognition Jaes L. Crowley osig 1 Winter Seester 2018 Lesson 6 27 February 2018 Outline Perceptrons and Support Vector achines Notation...2 Linear odels...3 Lines, Planes

More information

Using EM To Estimate A Probablity Density With A Mixture Of Gaussians

Using EM To Estimate A Probablity Density With A Mixture Of Gaussians Using EM To Estiate A Probablity Density With A Mixture Of Gaussians Aaron A. D Souza adsouza@usc.edu Introduction The proble we are trying to address in this note is siple. Given a set of data points

More information

A Decision-Based Model and Algorithm for Maneuvering Target Tracking

A Decision-Based Model and Algorithm for Maneuvering Target Tracking WSEAS RANSACIONS on SYSEMS A Decision-Based Model and Algorith for Maneuvering arget racking JIAHONG CHEN ZHONGHUA ZHANG ZHENDONG XI YONGXING MAO China Satellite Maritie racking and Control Departent,

More information

Smoothing Framework for Automatic Track Initiation in Clutter

Smoothing Framework for Automatic Track Initiation in Clutter Soothing Fraework for Autoatic Track Initiation in Clutter Rajib Chakravorty Networked Sensor Technology (NeST) Laboratory Faculty of Engineering University of Technology, Sydney Broadway -27,Sydney, NSW

More information

Detection and Estimation Theory

Detection and Estimation Theory ESE 54 Detection and Estiation Theory Joseph A. O Sullivan Sauel C. Sachs Professor Electronic Systes and Signals Research Laboratory Electrical and Systes Engineering Washington University 11 Urbauer

More information

Handwriting Detection Model Based on Four-Dimensional Vector Space Model

Handwriting Detection Model Based on Four-Dimensional Vector Space Model Journal of Matheatics Research; Vol. 10, No. 4; August 2018 ISSN 1916-9795 E-ISSN 1916-9809 Published by Canadian Center of Science and Education Handwriting Detection Model Based on Four-Diensional Vector

More information

Multiscale Entropy Analysis: A New Method to Detect Determinism in a Time. Series. A. Sarkar and P. Barat. Variable Energy Cyclotron Centre

Multiscale Entropy Analysis: A New Method to Detect Determinism in a Time. Series. A. Sarkar and P. Barat. Variable Energy Cyclotron Centre Multiscale Entropy Analysis: A New Method to Detect Deterinis in a Tie Series A. Sarkar and P. Barat Variable Energy Cyclotron Centre /AF Bidhan Nagar, Kolkata 700064, India PACS nubers: 05.45.Tp, 89.75.-k,

More information

Warning System of Dangerous Chemical Gas in Factory Based on Wireless Sensor Network

Warning System of Dangerous Chemical Gas in Factory Based on Wireless Sensor Network 565 A publication of CHEMICAL ENGINEERING TRANSACTIONS VOL. 59, 07 Guest Editors: Zhuo Yang, Junie Ba, Jing Pan Copyright 07, AIDIC Servizi S.r.l. ISBN 978-88-95608-49-5; ISSN 83-96 The Italian Association

More information

Fairness via priority scheduling

Fairness via priority scheduling Fairness via priority scheduling Veeraruna Kavitha, N Heachandra and Debayan Das IEOR, IIT Bobay, Mubai, 400076, India vavitha,nh,debayan}@iitbacin Abstract In the context of ulti-agent resource allocation

More information

PULSE-TRAIN BASED TIME-DELAY ESTIMATION IMPROVES RESILIENCY TO NOISE

PULSE-TRAIN BASED TIME-DELAY ESTIMATION IMPROVES RESILIENCY TO NOISE PULSE-TRAIN BASED TIME-DELAY ESTIMATION IMPROVES RESILIENCY TO NOISE 1 Nicola Neretti, 1 Nathan Intrator and 1,2 Leon N Cooper 1 Institute for Brain and Neural Systes, Brown University, Providence RI 02912.

More information

State Estimation Problem for the Action Potential Modeling in Purkinje Fibers

State Estimation Problem for the Action Potential Modeling in Purkinje Fibers APCOM & ISCM -4 th Deceber, 203, Singapore State Estiation Proble for the Action Potential Modeling in Purinje Fibers *D. C. Estuano¹, H. R. B.Orlande and M. J.Colaço Federal University of Rio de Janeiro

More information

Department of Physics, Sri Venkateswara University, Tirupati Range Operations, Satish Dhawan Space Centre SHAR, ISRO, Sriharikota

Department of Physics, Sri Venkateswara University, Tirupati Range Operations, Satish Dhawan Space Centre SHAR, ISRO, Sriharikota Trajectory Estiation of a Satellite Launch Vehicle Using Unscented Kalan Filter fro Noisy Radar Measureents R.Varaprasad S.V. Bhaskara Rao D.Narayana Rao V. Seshagiri Rao Range Operations, Satish Dhawan

More information

Inspection; structural health monitoring; reliability; Bayesian analysis; updating; decision analysis; value of information

Inspection; structural health monitoring; reliability; Bayesian analysis; updating; decision analysis; value of information Cite as: Straub D. (2014). Value of inforation analysis with structural reliability ethods. Structural Safety, 49: 75-86. Value of Inforation Analysis with Structural Reliability Methods Daniel Straub

More information

Non-Parametric Non-Line-of-Sight Identification 1

Non-Parametric Non-Line-of-Sight Identification 1 Non-Paraetric Non-Line-of-Sight Identification Sinan Gezici, Hisashi Kobayashi and H. Vincent Poor Departent of Electrical Engineering School of Engineering and Applied Science Princeton University, Princeton,

More information

Support Vector Machine Classification of Uncertain and Imbalanced data using Robust Optimization

Support Vector Machine Classification of Uncertain and Imbalanced data using Robust Optimization Recent Researches in Coputer Science Support Vector Machine Classification of Uncertain and Ibalanced data using Robust Optiization RAGHAV PAT, THEODORE B. TRAFALIS, KASH BARKER School of Industrial Engineering

More information

Analyzing Simulation Results

Analyzing Simulation Results Analyzing Siulation Results Dr. John Mellor-Cruey Departent of Coputer Science Rice University johnc@cs.rice.edu COMP 528 Lecture 20 31 March 2005 Topics for Today Model verification Model validation Transient

More information

Estimating Parameters for a Gaussian pdf

Estimating Parameters for a Gaussian pdf Pattern Recognition and achine Learning Jaes L. Crowley ENSIAG 3 IS First Seester 00/0 Lesson 5 7 Noveber 00 Contents Estiating Paraeters for a Gaussian pdf Notation... The Pattern Recognition Proble...3

More information

Bayes Decision Rule and Naïve Bayes Classifier

Bayes Decision Rule and Naïve Bayes Classifier Bayes Decision Rule and Naïve Bayes Classifier Le Song Machine Learning I CSE 6740, Fall 2013 Gaussian Mixture odel A density odel p(x) ay be ulti-odal: odel it as a ixture of uni-odal distributions (e.g.

More information

Pattern Recognition and Machine Learning. Learning and Evaluation for Pattern Recognition

Pattern Recognition and Machine Learning. Learning and Evaluation for Pattern Recognition Pattern Recognition and Machine Learning Jaes L. Crowley ENSIMAG 3 - MMIS Fall Seester 2017 Lesson 1 4 October 2017 Outline Learning and Evaluation for Pattern Recognition Notation...2 1. The Pattern Recognition

More information

MSEC MODELING OF DEGRADATION PROCESSES TO OBTAIN AN OPTIMAL SOLUTION FOR MAINTENANCE AND PERFORMANCE

MSEC MODELING OF DEGRADATION PROCESSES TO OBTAIN AN OPTIMAL SOLUTION FOR MAINTENANCE AND PERFORMANCE Proceeding of the ASME 9 International Manufacturing Science and Engineering Conference MSEC9 October 4-7, 9, West Lafayette, Indiana, USA MSEC9-8466 MODELING OF DEGRADATION PROCESSES TO OBTAIN AN OPTIMAL

More information

A Formulation of Multitarget Tracking as an Incomplete Data Problem

A Formulation of Multitarget Tracking as an Incomplete Data Problem I. INTRODUCTION A Forulation of Multitarget Tracing as an Incoplete Data Proble H. GAUVRIT J. P LE CADRE IRISA/CNRS France C. JAUFFRET DCN/Ingénierie/Sud France Traditional ultihypothesis tracing ethods

More information

UAV collision avoidance based on geometric approach

UAV collision avoidance based on geometric approach Loughborough University Institutional Repository UV collision avoidance based on geoetric approach This ite was subitted to Loughborough University's Institutional Repository by the/an author. Citation:

More information

SPECTRUM sensing is a core concept of cognitive radio

SPECTRUM sensing is a core concept of cognitive radio World Acadey of Science, Engineering and Technology International Journal of Electronics and Counication Engineering Vol:6, o:2, 202 Efficient Detection Using Sequential Probability Ratio Test in Mobile

More information

Symbolic Analysis as Universal Tool for Deriving Properties of Non-linear Algorithms Case study of EM Algorithm

Symbolic Analysis as Universal Tool for Deriving Properties of Non-linear Algorithms Case study of EM Algorithm Acta Polytechnica Hungarica Vol., No., 04 Sybolic Analysis as Universal Tool for Deriving Properties of Non-linear Algoriths Case study of EM Algorith Vladiir Mladenović, Miroslav Lutovac, Dana Porrat

More information

Using a De-Convolution Window for Operating Modal Analysis

Using a De-Convolution Window for Operating Modal Analysis Using a De-Convolution Window for Operating Modal Analysis Brian Schwarz Vibrant Technology, Inc. Scotts Valley, CA Mark Richardson Vibrant Technology, Inc. Scotts Valley, CA Abstract Operating Modal Analysis

More information

Interactive Markov Models of Evolutionary Algorithms

Interactive Markov Models of Evolutionary Algorithms Cleveland State University EngagedScholarship@CSU Electrical Engineering & Coputer Science Faculty Publications Electrical Engineering & Coputer Science Departent 2015 Interactive Markov Models of Evolutionary

More information

Bayesian Terrain-Based Underwater Navigation Using an Improved State-Space Model

Bayesian Terrain-Based Underwater Navigation Using an Improved State-Space Model Bayesian Terrain-Based Underwater Navigation Using an Iproved State-Space Model Kjetil Bergh Ånonsen Departent of Engineering Cybernetics, Norwegian University of Science and Technology, NO-7491 Trondhei,

More information

Multi-Scale/Multi-Resolution: Wavelet Transform

Multi-Scale/Multi-Resolution: Wavelet Transform Multi-Scale/Multi-Resolution: Wavelet Transfor Proble with Fourier Fourier analysis -- breaks down a signal into constituent sinusoids of different frequencies. A serious drawback in transforing to the

More information

Use of PSO in Parameter Estimation of Robot Dynamics; Part One: No Need for Parameterization

Use of PSO in Parameter Estimation of Robot Dynamics; Part One: No Need for Parameterization Use of PSO in Paraeter Estiation of Robot Dynaics; Part One: No Need for Paraeterization Hossein Jahandideh, Mehrzad Navar Abstract Offline procedures for estiating paraeters of robot dynaics are practically

More information

Nonmonotonic Networks. a. IRST, I Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I Povo (Trento) Italy

Nonmonotonic Networks. a. IRST, I Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I Povo (Trento) Italy Storage Capacity and Dynaics of Nononotonic Networks Bruno Crespi a and Ignazio Lazzizzera b a. IRST, I-38050 Povo (Trento) Italy, b. Univ. of Trento, Physics Dept., I-38050 Povo (Trento) Italy INFN Gruppo

More information

A New Approach to Solving Dynamic Traveling Salesman Problems

A New Approach to Solving Dynamic Traveling Salesman Problems A New Approach to Solving Dynaic Traveling Salesan Probles Changhe Li 1 Ming Yang 1 Lishan Kang 1 1 China University of Geosciences(Wuhan) School of Coputer 4374 Wuhan,P.R.China lchwfx@yahoo.co,yanging72@gail.co,ang_whu@yahoo.co

More information

Multitarget tracking via joint PHD filtering and multiscan association

Multitarget tracking via joint PHD filtering and multiscan association 1th International Conference on Inforation Fusion Seattle, WA, USA, July 6-9, 9 Multitarget tracing via joint PHD filtering and ultiscan association F. Papi, G. Battistelli, L.Chisci, S. Morrocchi Dip.

More information

Polygonal Designs: Existence and Construction

Polygonal Designs: Existence and Construction Polygonal Designs: Existence and Construction John Hegean Departent of Matheatics, Stanford University, Stanford, CA 9405 Jeff Langford Departent of Matheatics, Drake University, Des Moines, IA 5011 G

More information

3D acoustic wave modeling with a time-space domain dispersion-relation-based Finite-difference scheme

3D acoustic wave modeling with a time-space domain dispersion-relation-based Finite-difference scheme P-8 3D acoustic wave odeling with a tie-space doain dispersion-relation-based Finite-difference schee Yang Liu * and rinal K. Sen State Key Laboratory of Petroleu Resource and Prospecting (China University

More information

Sharp Time Data Tradeoffs for Linear Inverse Problems

Sharp Time Data Tradeoffs for Linear Inverse Problems Sharp Tie Data Tradeoffs for Linear Inverse Probles Saet Oyak Benjain Recht Mahdi Soltanolkotabi January 016 Abstract In this paper we characterize sharp tie-data tradeoffs for optiization probles used

More information

A method to determine relative stroke detection efficiencies from multiplicity distributions

A method to determine relative stroke detection efficiencies from multiplicity distributions A ethod to deterine relative stroke detection eiciencies ro ultiplicity distributions Schulz W. and Cuins K. 2. Austrian Lightning Detection and Inoration Syste (ALDIS), Kahlenberger Str.2A, 90 Vienna,

More information

Condition Monitoring and Fault Detection of Railway Vehicle Suspension using Multiple-Model Approach

Condition Monitoring and Fault Detection of Railway Vehicle Suspension using Multiple-Model Approach Proceedings of the 17th World Congress The International Federation of Autoatic Control Condition Monitoring and Fault Detection of Railway Vehicle Suspension using Multiple-Model Approach Hitoshi Tsunashia

More information

Machine Learning Basics: Estimators, Bias and Variance

Machine Learning Basics: Estimators, Bias and Variance Machine Learning Basics: Estiators, Bias and Variance Sargur N. srihari@cedar.buffalo.edu This is part of lecture slides on Deep Learning: http://www.cedar.buffalo.edu/~srihari/cse676 1 Topics in Basics

More information

Fast Structural Similarity Search of Noncoding RNAs Based on Matched Filtering of Stem Patterns

Fast Structural Similarity Search of Noncoding RNAs Based on Matched Filtering of Stem Patterns Fast Structural Siilarity Search of Noncoding RNs Based on Matched Filtering of Ste Patterns Byung-Jun Yoon Dept. of Electrical Engineering alifornia Institute of Technology Pasadena, 91125, S Eail: bjyoon@caltech.edu

More information

Combining Classifiers

Combining Classifiers Cobining Classifiers Generic ethods of generating and cobining ultiple classifiers Bagging Boosting References: Duda, Hart & Stork, pg 475-480. Hastie, Tibsharini, Friedan, pg 246-256 and Chapter 10. http://www.boosting.org/

More information

Model Fitting. CURM Background Material, Fall 2014 Dr. Doreen De Leon

Model Fitting. CURM Background Material, Fall 2014 Dr. Doreen De Leon Model Fitting CURM Background Material, Fall 014 Dr. Doreen De Leon 1 Introduction Given a set of data points, we often want to fit a selected odel or type to the data (e.g., we suspect an exponential

More information

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation

Course Notes for EE227C (Spring 2018): Convex Optimization and Approximation Course Notes for EE227C (Spring 2018): Convex Optiization and Approxiation Instructor: Moritz Hardt Eail: hardt+ee227c@berkeley.edu Graduate Instructor: Max Sichowitz Eail: sichow+ee227c@berkeley.edu October

More information

This model assumes that the probability of a gap has size i is proportional to 1/i. i.e., i log m e. j=1. E[gap size] = i P r(i) = N f t.

This model assumes that the probability of a gap has size i is proportional to 1/i. i.e., i log m e. j=1. E[gap size] = i P r(i) = N f t. CS 493: Algoriths for Massive Data Sets Feb 2, 2002 Local Models, Bloo Filter Scribe: Qin Lv Local Models In global odels, every inverted file entry is copressed with the sae odel. This work wells when

More information

Supervised Baysian SAR image Classification Using The Full Polarimetric Data

Supervised Baysian SAR image Classification Using The Full Polarimetric Data Supervised Baysian SAR iage Classification Using The Full Polarietric Data (1) () Ziad BELHADJ (1) SUPCOM, Route de Raoued 3.5 083 El Ghazala - TUNSA () ENT, BP. 37, 100 Tunis Belvedere, TUNSA Abstract

More information

Data-Driven Imaging in Anisotropic Media

Data-Driven Imaging in Anisotropic Media 18 th World Conference on Non destructive Testing, 16- April 1, Durban, South Africa Data-Driven Iaging in Anisotropic Media Arno VOLKER 1 and Alan HUNTER 1 TNO Stieltjesweg 1, 6 AD, Delft, The Netherlands

More information

Pattern Recognition and Machine Learning. Artificial Neural networks

Pattern Recognition and Machine Learning. Artificial Neural networks Pattern Recognition and Machine Learning Jaes L. Crowley ENSIMAG 3 - MMIS Fall Seester 2016 Lessons 7 14 Dec 2016 Outline Artificial Neural networks Notation...2 1. Introduction...3... 3 The Artificial

More information

REPORT DOCUMENTATION PAGE

REPORT DOCUMENTATION PAGE EPOT DOCUMENTATION PAGE For Approved OMB NO. 74-188 The public reporting burden for this collection of inforation is estiated to average 1 hour per response, including the tie for reviewing instructions,

More information

J11.3 STOCHASTIC EVENT RECONSTRUCTION OF ATMOSPHERIC CONTAMINANT DISPERSION

J11.3 STOCHASTIC EVENT RECONSTRUCTION OF ATMOSPHERIC CONTAMINANT DISPERSION J11.3 STOCHASTIC EVENT RECONSTRUCTION OF ATMOSPHERIC CONTAMINANT DISPERSION Inanc Senocak 1*, Nicolas W. Hengartner, Margaret B. Short 3, and Brent W. Daniel 1 Boise State University, Boise, ID, Los Alaos

More information

THE KALMAN FILTER: A LOOK BEHIND THE SCENE

THE KALMAN FILTER: A LOOK BEHIND THE SCENE HE KALMA FILER: A LOOK BEHID HE SCEE R.E. Deain School of Matheatical and Geospatial Sciences, RMI University eail: rod.deain@rit.edu.au Presented at the Victorian Regional Survey Conference, Mildura,

More information

Adapting the Pheromone Evaporation Rate in Dynamic Routing Problems

Adapting the Pheromone Evaporation Rate in Dynamic Routing Problems Adapting the Pheroone Evaporation Rate in Dynaic Routing Probles Michalis Mavrovouniotis and Shengxiang Yang School of Coputer Science and Inforatics, De Montfort University The Gateway, Leicester LE1

More information

Asynchronous Gossip Algorithms for Stochastic Optimization

Asynchronous Gossip Algorithms for Stochastic Optimization Asynchronous Gossip Algoriths for Stochastic Optiization S. Sundhar Ra ECE Dept. University of Illinois Urbana, IL 680 ssrini@illinois.edu A. Nedić IESE Dept. University of Illinois Urbana, IL 680 angelia@illinois.edu

More information

ESTIMATING AND FORMING CONFIDENCE INTERVALS FOR EXTREMA OF RANDOM POLYNOMIALS. A Thesis. Presented to. The Faculty of the Department of Mathematics

ESTIMATING AND FORMING CONFIDENCE INTERVALS FOR EXTREMA OF RANDOM POLYNOMIALS. A Thesis. Presented to. The Faculty of the Department of Mathematics ESTIMATING AND FORMING CONFIDENCE INTERVALS FOR EXTREMA OF RANDOM POLYNOMIALS A Thesis Presented to The Faculty of the Departent of Matheatics San Jose State University In Partial Fulfillent of the Requireents

More information

Ch 12: Variations on Backpropagation

Ch 12: Variations on Backpropagation Ch 2: Variations on Backpropagation The basic backpropagation algorith is too slow for ost practical applications. It ay take days or weeks of coputer tie. We deonstrate why the backpropagation algorith

More information

2nd Workshop on Joints Modelling Dartington April 2009 Identification of Nonlinear Bolted Lap Joint Parameters using Force State Mapping

2nd Workshop on Joints Modelling Dartington April 2009 Identification of Nonlinear Bolted Lap Joint Parameters using Force State Mapping Identification of Nonlinear Bolted Lap Joint Paraeters using Force State Mapping International Journal of Solids and Structures, 44 (007) 8087 808 Hassan Jalali, Haed Ahadian and John E Mottershead _ Γ

More information

COS 424: Interacting with Data. Written Exercises

COS 424: Interacting with Data. Written Exercises COS 424: Interacting with Data Hoework #4 Spring 2007 Regression Due: Wednesday, April 18 Written Exercises See the course website for iportant inforation about collaboration and late policies, as well

More information

A MESHSIZE BOOSTING ALGORITHM IN KERNEL DENSITY ESTIMATION

A MESHSIZE BOOSTING ALGORITHM IN KERNEL DENSITY ESTIMATION A eshsize boosting algorith in kernel density estiation A MESHSIZE BOOSTING ALGORITHM IN KERNEL DENSITY ESTIMATION C.C. Ishiekwene, S.M. Ogbonwan and J.E. Osewenkhae Departent of Matheatics, University

More information

Bayesian Approach for Fatigue Life Prediction from Field Inspection

Bayesian Approach for Fatigue Life Prediction from Field Inspection Bayesian Approach for Fatigue Life Prediction fro Field Inspection Dawn An and Jooho Choi School of Aerospace & Mechanical Engineering, Korea Aerospace University, Goyang, Seoul, Korea Srira Pattabhiraan

More information

Ştefan ŞTEFĂNESCU * is the minimum global value for the function h (x)

Ştefan ŞTEFĂNESCU * is the minimum global value for the function h (x) 7Applying Nelder Mead s Optiization Algorith APPLYING NELDER MEAD S OPTIMIZATION ALGORITHM FOR MULTIPLE GLOBAL MINIMA Abstract Ştefan ŞTEFĂNESCU * The iterative deterinistic optiization ethod could not

More information

Bayesian inference for stochastic differential mixed effects models - initial steps

Bayesian inference for stochastic differential mixed effects models - initial steps Bayesian inference for stochastic differential ixed effects odels - initial steps Gavin Whitaker 2nd May 2012 Supervisors: RJB and AG Outline Mixed Effects Stochastic Differential Equations (SDEs) Bayesian

More information

Automated Frequency Domain Decomposition for Operational Modal Analysis

Automated Frequency Domain Decomposition for Operational Modal Analysis Autoated Frequency Doain Decoposition for Operational Modal Analysis Rune Brincker Departent of Civil Engineering, University of Aalborg, Sohngaardsholsvej 57, DK-9000 Aalborg, Denark Palle Andersen Structural

More information

Decentralized Adaptive Control of Nonlinear Systems Using Radial Basis Neural Networks

Decentralized Adaptive Control of Nonlinear Systems Using Radial Basis Neural Networks 050 IEEE TRANSACTIONS ON AUTOMATIC CONTROL, VOL. 44, NO., NOVEMBER 999 Decentralized Adaptive Control of Nonlinear Systes Using Radial Basis Neural Networks Jeffrey T. Spooner and Kevin M. Passino Abstract

More information

W-BASED VS LATENT VARIABLES SPATIAL AUTOREGRESSIVE MODELS: EVIDENCE FROM MONTE CARLO SIMULATIONS

W-BASED VS LATENT VARIABLES SPATIAL AUTOREGRESSIVE MODELS: EVIDENCE FROM MONTE CARLO SIMULATIONS W-BASED VS LATENT VARIABLES SPATIAL AUTOREGRESSIVE MODELS: EVIDENCE FROM MONTE CARLO SIMULATIONS. Introduction When it coes to applying econoetric odels to analyze georeferenced data, researchers are well

More information

A remark on a success rate model for DPA and CPA

A remark on a success rate model for DPA and CPA A reark on a success rate odel for DPA and CPA A. Wieers, BSI Version 0.5 andreas.wieers@bsi.bund.de Septeber 5, 2018 Abstract The success rate is the ost coon evaluation etric for easuring the perforance

More information

Extension of CSRSM for the Parametric Study of the Face Stability of Pressurized Tunnels

Extension of CSRSM for the Parametric Study of the Face Stability of Pressurized Tunnels Extension of CSRSM for the Paraetric Study of the Face Stability of Pressurized Tunnels Guilhe Mollon 1, Daniel Dias 2, and Abdul-Haid Soubra 3, M.ASCE 1 LGCIE, INSA Lyon, Université de Lyon, Doaine scientifique

More information

Figure 1: Equivalent electric (RC) circuit of a neurons membrane

Figure 1: Equivalent electric (RC) circuit of a neurons membrane Exercise: Leaky integrate and fire odel of neural spike generation This exercise investigates a siplified odel of how neurons spike in response to current inputs, one of the ost fundaental properties of

More information

International Scientific and Technological Conference EXTREME ROBOTICS October 8-9, 2015, Saint-Petersburg, Russia

International Scientific and Technological Conference EXTREME ROBOTICS October 8-9, 2015, Saint-Petersburg, Russia International Scientific and Technological Conference EXTREME ROBOTICS October 8-9, 215, Saint-Petersburg, Russia LEARNING MOBILE ROBOT BASED ON ADAPTIVE CONTROLLED MARKOV CHAINS V.Ya. Vilisov University

More information

System Design of Quadrotor

System Design of Quadrotor Syste Design of Quadrotor Yukai Gong, Weina Mao, Bu Fan, Yi Yang Mar. 29, 2016 A final project of MECHENG 561. Supervised by Prof. Vasudevan. 1 Abstract In this report, an autonoous quadrotor is designed.

More information

Neural Network-Aided Extended Kalman Filter for SLAM Problem

Neural Network-Aided Extended Kalman Filter for SLAM Problem 7 IEEE International Conference on Robotics and Autoation Roa, Italy, -4 April 7 ThA.5 Neural Network-Aided Extended Kalan Filter for SLAM Proble Minyong Choi, R. Sakthivel, and Wan Kyun Chung Abstract

More information

Pattern Recognition and Machine Learning. Artificial Neural networks

Pattern Recognition and Machine Learning. Artificial Neural networks Pattern Recognition and Machine Learning Jaes L. Crowley ENSIMAG 3 - MMIS Fall Seester 2016/2017 Lessons 9 11 Jan 2017 Outline Artificial Neural networks Notation...2 Convolutional Neural Networks...3

More information

HIGH RESOLUTION NEAR-FIELD MULTIPLE TARGET DETECTION AND LOCALIZATION USING SUPPORT VECTOR MACHINES

HIGH RESOLUTION NEAR-FIELD MULTIPLE TARGET DETECTION AND LOCALIZATION USING SUPPORT VECTOR MACHINES ICONIC 2007 St. Louis, O, USA June 27-29, 2007 HIGH RESOLUTION NEAR-FIELD ULTIPLE TARGET DETECTION AND LOCALIZATION USING SUPPORT VECTOR ACHINES A. Randazzo,. A. Abou-Khousa 2,.Pastorino, and R. Zoughi

More information

Statistical Logic Cell Delay Analysis Using a Current-based Model

Statistical Logic Cell Delay Analysis Using a Current-based Model Statistical Logic Cell Delay Analysis Using a Current-based Model Hanif Fatei Shahin Nazarian Massoud Pedra Dept. of EE-Systes, University of Southern California, Los Angeles, CA 90089 {fatei, shahin,

More information

Recovering Data from Underdetermined Quadratic Measurements (CS 229a Project: Final Writeup)

Recovering Data from Underdetermined Quadratic Measurements (CS 229a Project: Final Writeup) Recovering Data fro Underdeterined Quadratic Measureents (CS 229a Project: Final Writeup) Mahdi Soltanolkotabi Deceber 16, 2011 1 Introduction Data that arises fro engineering applications often contains

More information

Estimation of ADC Nonlinearities from the Measurement in Input Voltage Intervals

Estimation of ADC Nonlinearities from the Measurement in Input Voltage Intervals Estiation of ADC Nonlinearities fro the Measureent in Input Voltage Intervals M. Godla, L. Michaeli, 3 J. Šaliga, 4 R. Palenčár,,3 Deptartent of Electronics and Multiedia Counications, FEI TU of Košice,

More information

Multi-Dimensional Hegselmann-Krause Dynamics

Multi-Dimensional Hegselmann-Krause Dynamics Multi-Diensional Hegselann-Krause Dynaics A. Nedić Industrial and Enterprise Systes Engineering Dept. University of Illinois Urbana, IL 680 angelia@illinois.edu B. Touri Coordinated Science Laboratory

More information

Pseudo-marginal Metropolis-Hastings: a simple explanation and (partial) review of theory

Pseudo-marginal Metropolis-Hastings: a simple explanation and (partial) review of theory Pseudo-arginal Metropolis-Hastings: a siple explanation and (partial) review of theory Chris Sherlock Motivation Iagine a stochastic process V which arises fro soe distribution with density p(v θ ). Iagine

More information

A Simulation Study for Practical Control of a Quadrotor

A Simulation Study for Practical Control of a Quadrotor A Siulation Study for Practical Control of a Quadrotor Jeongho Noh* and Yongkyu Song** *Graduate student, Ph.D. progra, ** Ph.D., Professor Departent of Aerospace and Mechanical Engineering, Korea Aerospace

More information

Proc. of the IEEE/OES Seventh Working Conference on Current Measurement Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES

Proc. of the IEEE/OES Seventh Working Conference on Current Measurement Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES Proc. of the IEEE/OES Seventh Working Conference on Current Measureent Technology UNCERTAINTIES IN SEASONDE CURRENT VELOCITIES Belinda Lipa Codar Ocean Sensors 15 La Sandra Way, Portola Valley, CA 98 blipa@pogo.co

More information

Quantum algorithms (CO 781, Winter 2008) Prof. Andrew Childs, University of Waterloo LECTURE 15: Unstructured search and spatial search

Quantum algorithms (CO 781, Winter 2008) Prof. Andrew Childs, University of Waterloo LECTURE 15: Unstructured search and spatial search Quantu algoriths (CO 781, Winter 2008) Prof Andrew Childs, University of Waterloo LECTURE 15: Unstructured search and spatial search ow we begin to discuss applications of quantu walks to search algoriths

More information

Robustness Experiments for a Planar Hopping Control System

Robustness Experiments for a Planar Hopping Control System To appear in International Conference on Clibing and Walking Robots Septeber 22 Robustness Experients for a Planar Hopping Control Syste Kale Harbick and Gaurav S. Sukhate kale gaurav@robotics.usc.edu

More information

A model reduction approach to numerical inversion for a parabolic partial differential equation

A model reduction approach to numerical inversion for a parabolic partial differential equation Inverse Probles Inverse Probles 30 (204) 250 (33pp) doi:0.088/0266-56/30/2/250 A odel reduction approach to nuerical inversion for a parabolic partial differential equation Liliana Borcea, Vladiir Drusin

More information

Principal Components Analysis

Principal Components Analysis Principal Coponents Analysis Cheng Li, Bingyu Wang Noveber 3, 204 What s PCA Principal coponent analysis (PCA) is a statistical procedure that uses an orthogonal transforation to convert a set of observations

More information

arxiv: v2 [math.co] 3 Dec 2008

arxiv: v2 [math.co] 3 Dec 2008 arxiv:0805.2814v2 [ath.co] 3 Dec 2008 Connectivity of the Unifor Rando Intersection Graph Sion R. Blacburn and Stefanie Gere Departent of Matheatics Royal Holloway, University of London Egha, Surrey TW20

More information